© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6320
    Prev
    Next
    INDEX
    Explanations

    and

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is strongly activated by plural noun forms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    0.87
    ↵↵
    0.69
     lorsque
    0.66
     Los
    0.65
     David
    0.65
     Philadelphia
    0.65
     (
    0.64
     National
    0.64
     "
    0.64
     Boston
    0.64
    POSITIVE LOGITS
     ਅਤੇ
    0.82
     एवं
    0.80
     maupun
    0.80
    間の
    0.75
    及び
    0.74
     zakres
    0.73
     மற்றும்
    0.72
     ও
    0.70
     ಮತ್ತು
    0.70
     અને
    0.69
    Activations Density 0.000%

    No Known Activations